翻译中的迷失：生成对往返翻译具有鲁棒性的对抗样本
Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation
AI总结：
该研究针对文本对抗样本经往返翻译后失效的问题，全面验证了6种主流文本对抗攻击的跨翻译鲁棒性不足，提出将机器翻译融入生成过程的干预方案提升鲁棒性，为多语言语言模型缺陷识别与对抗攻击研究提供参考。
摘要：
当前的语言模型在大量下游任务中均能实现高准确率。然而，它们仍易受对抗攻击的影响，尤其是那些对抗样本与原文保持高度相似性的攻击。鉴于文本的多语言属性，对抗样本在跨翻译场景下的有效性，以及机器翻译如何提升对抗样本的鲁棒性，目前在很大程度上仍未被探究。本文针对当前文本对抗攻击对往返翻译的鲁棒性展开了全面研究。我们证实，6种最先进的基于文本的对抗攻击在经过往返翻译后均无法维持其攻击效能。此外，我们提出了一种基于干预的解决方案，将机器翻译（Machine Translation）融入对抗样本生成过程，并证明该方法提升了对抗样本对往返翻译的鲁棒性。我们的研究结果表明，找到对翻译具有鲁棒性的对抗样本，有助于识别语言模型在跨语言场景下普遍存在的不足，并推动多语言对抗攻击领域的进一步研究。
英文摘要：
Language Models today provide a high accuracy across a large number of downstream tasks. However, they remain susceptible to adversarial attacks, particularly against those where the adversarial examples maintain considerable similarity to the original text. Given the multilingual nature of text, the effectiveness of adversarial examples across translations and how machine translations can improve the robustness of adversarial examples remain largely unexplored. In this paper, we present a comprehensive study on the robustness of current text adversarial attacks to round-trip translation. We demonstrate that 6 state-of-the-art text-based adversarial attacks do not maintain their efficacy after round-trip translation. Furthermore, we introduce an intervention-based solution to this problem, by integrating Machine Translation into the process of adversarial example generation and demonstrating increased robustness to round-trip translation. Our results indicate that finding adversarial examples robust to translation can help identify the insufficiency of language models that is common across languages, and motivate further research into multilingual adversarial attacks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
